library(tidyverse) # For data manipulation and visualization
## Warning: package 'tidyverse' was built under R version 4.2.3
## Warning: package 'ggplot2' was built under R version 4.2.3
## Warning: package 'tibble' was built under R version 4.2.3
## Warning: package 'readr' was built under R version 4.2.3
## Warning: package 'dplyr' was built under R version 4.2.3
## Warning: package 'forcats' was built under R version 4.2.3
## Warning: package 'lubridate' was built under R version 4.2.3
## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr 1.1.1 ✔ readr 2.1.4
## ✔ forcats 1.0.0 ✔ stringr 1.5.0
## ✔ ggplot2 3.4.2 ✔ tibble 3.2.1
## ✔ lubridate 1.9.2 ✔ tidyr 1.3.0
## ✔ purrr 1.0.1
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag() masks stats::lag()
## ℹ Use the ]8;;http://conflicted.r-lib.org/conflicted package]8;; to force all conflicts to become errors
library(lubridate) # For working with date-time data
library("ggplot2")
library(plotly)
## Warning: package 'plotly' was built under R version 4.2.3
##
## Attaching package: 'plotly'
##
## The following object is masked from 'package:ggplot2':
##
## last_plot
##
## The following object is masked from 'package:stats':
##
## filter
##
## The following object is masked from 'package:graphics':
##
## layout
library(leaflet)
library(leaflet.extras)
## Warning: package 'leaflet.extras' was built under R version 4.2.3
# Load data
data <- read.csv("DataCoSupplyChainDataset.csv")
data_description <- read.csv("DescriptionDataCoSupplyChain.csv")
# Display summary statistics for numerical variables
summary(data[, c("Days.for.shipping..real.","Days.for.shipment..scheduled.","Benefit.per.order","Sales.per.customer")])
## Days.for.shipping..real. Days.for.shipment..scheduled. Benefit.per.order
## Min. :0.000 Min. :0.000 Min. :-4274.98
## 1st Qu.:2.000 1st Qu.:2.000 1st Qu.: 7.00
## Median :3.000 Median :4.000 Median : 31.52
## Mean :3.498 Mean :2.932 Mean : 21.98
## 3rd Qu.:5.000 3rd Qu.:4.000 3rd Qu.: 64.80
## Max. :6.000 Max. :4.000 Max. : 911.80
## Sales.per.customer
## Min. : 7.49
## 1st Qu.: 104.38
## Median : 163.99
## Mean : 183.11
## 3rd Qu.: 247.40
## Max. :1939.99
# Create a histogram of sales per customer
ggplot(data, aes(x = `Sales.per.customer`)) +
geom_histogram() +
labs(x = "Sales per customer", y = "Count", title = "Distribution of Sales per Customer")
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
# Create a bar chart of delivery status
ggplot(data, aes(x = `Delivery.Status`)) +
geom_bar() +
labs(x = "Delivery Status", y = "Count", title = "Delivery Status Distribution")
ggplot(data, aes(x = Late_delivery_risk, fill = Delivery.Status)) +
geom_density(alpha = 0.5) +
labs(title = "Late Delivery Risk by Delivery Status")
ggplot(data, aes(x = Category.Name, y = Sales, fill = Category.Name)) +
geom_boxplot() +
labs(title = "Category Name vs. Sales")
ggplot(data, aes(x = Shipping.Mode, y = Late_delivery_risk, fill = Shipping.Mode)) +
geom_boxplot() +
labs(title = "Shipping Mode vs. Late Delivery Risk")
# Highest revenue based on Department.
sales_by_deapartmnet <- aggregate(data$Sales, by = list(Department = data$Department.Name), FUN = sum)
# create the plot
d <- ggplot(sales_by_deapartmnet, aes(x = Department, y = x, fill = Department, text = paste("Department: ", Department, "<br>", "Sales: $", x))) +
geom_bar(stat = "identity") +
labs(title = "Total Sales by Department") +
xlab("Department") +
ylab("Sales") +
theme(axis.text.x = element_text(angle = 90, vjust = 0.5, hjust=1))
# convert the plot to plotly
ggplotly(d)
#Top 10 countries which are selling porduct to the customers.
# calculate the count of orders by Order.Country
orders_by_country <- data %>%
group_by(Order.Country) %>%
summarize(count = n()) %>%
arrange(desc(count)) %>%
slice(1:10)
#Error in the output Because of mexico
# create the plot
p <- ggplot(orders_by_country, aes(x = Order.Country, y = count, fill = Order.Country, text = paste("Country: ", Order.Country, "<br>", "Orders: ", count))) +
geom_bar(stat = "identity") +
labs(title = "Top 10 Order Countries by Customer Orders") +
xlab("Order Country") +
ylab("Customer Orders") +
theme(axis.text.x = element_text(angle = 90, vjust = 0.5, hjust=1))
# convert the plot to plotly
ggplotly(p)
#Plotting the region based sales to the customers.
# create a data frame with the count of orders by order region
order_region_count <- data %>%
group_by(Order.Region) %>%
summarise(Count = n()) %>%
arrange(desc(Count))
# create the plot
plot <- ggplot(order_region_count, aes(x = Order.Region, y = Count, fill = Order.Region, text = paste("Order Region: ", Order.Region, "<br>", "Order Count: ", Count))) +
geom_bar(stat = "identity") +
labs(title = "Order Regions by Count of Orders from Customers") +
xlab("Order Region") +
ylab("Order Count") +
theme(axis.text.x = element_text(angle = 90, vjust = 0.5, hjust=1)) +
scale_fill_viridis_d()
# convert the plot to plotly
ggplotly(plot)
# get the top 20 customers who did the highest sales.
# create a data frame with sales per customer
sales_per_customer <- data %>%
group_by(Customer.Id) %>%
summarise(total_sales = sum(Sales)) %>%
arrange(desc(total_sales))
# get the top 20 customers who did the highest sales.
top_customers <- head(sales_per_customer, 20)
# create a new column with the combined first and last name of each customer
#Issue with row-1.
top_customers <- top_customers %>%
left_join(data %>% select(Customer.Id, Customer.Fname, Customer.Lname), by = "Customer.Id") %>%
mutate(CustomerName = paste(Customer.Fname, Customer.Lname, sep = " "))
# create the plot
plot <- ggplot(top_customers, aes(x = reorder(CustomerName, -total_sales), y = total_sales, fill = CustomerName, text = paste("Customer Name: ", CustomerName, "<br>", "Total Sales: $", total_sales))) +
geom_bar(stat = "identity") +
labs(title = "Top 20 Customers by Sales") +
xlab("Customer Name") +
ylab("Total Sales") +
theme(axis.text.x = element_text(angle = 90, vjust = 0.5, hjust=1))
# convert the plot to plotly
ggplotly(plot)
# Aggregate the data by Customer.City and calculate the total number of orders
Customer.City_orders <- data %>%
group_by(Customer.City, Latitude, Longitude) %>%
summarise(total_orders = n()) %>%
arrange(desc(total_orders))
## `summarise()` has grouped output by 'Customer.City', 'Latitude'. You can
## override using the `.groups` argument.
# Create color palette
colorPalette <- colorNumeric(palette = "YlOrRd", domain = Customer.City_orders$total_orders)
# Create heat map
# Set the initial view to focus on the US
m <- leaflet(Customer.City_orders) %>%
addTiles() %>%
setView(lng = -95.7129, lat = 37.0902, zoom = 4) %>%
addHeatmap(lng = ~Longitude, lat = ~Latitude, intensity = ~total_orders, blur = 20, max = max(Customer.City_orders$total_orders))
m